evomo.problems.neuroevolution.morobtrol.mo_walker2d#

Classes#

MoWalker2d

The multi-objective version of walker2d env.

Module Contents#

class evomo.problems.neuroevolution.morobtrol.mo_walker2d.MoWalker2d(**kwargs)#

Bases: brax.envs.walker2d.Walker2d

The multi-objective version of walker2d env.

References:

[1] C. D. Freeman, E. Frey, A. Raichuk, S. Girgin, I. Mordatch, and O. Bachem, “Brax - a differentiable physics engine for large scale rigid body simulation,” 2021. [Online]. Available: http://github.com/google/brax

Initialize the multi-objective walker2d env.

Parameters:

num_obj – The number of the objectives. For this env, it is set to 2.

num_obj = 2#
reset(rng)#
step(state: brax.envs.base.State, action: jax.Array)#

Run one timestep of the environment’s dynamics.

For more information, please refer to walker2d <https://github.com/google/brax/tree/main/brax/envs/walker2d.py> env in brax.